diff --git a/README.md b/README.md index ad389a0e..7ec675c0 100644 --- a/README.md +++ b/README.md @@ -1,138 +1,589 @@

- Anthropic Cybersecurity Skills + Anthropic Cybersecurity Skills β€” 734+ skills for AI agents

- 734+ cybersecurity skills for AI agents · agentskills.io open standard + License: Apache 2.0 + GitHub Stars + GitHub Forks + Last Commit + 734+ Skills + MITRE ATT&CK Mapped + Contributors

- License - Skills Count - Stars - Last Commit - Agent Skills - Platforms + The largest open-source collection of cybersecurity skills for AI agents.
734+ structured skills Β· MITRE ATT&CK mapped Β· NIST CSF 2.0 aligned Β· agentskills.io open standard +

+ +

+ 🌐 Landing Page Β· πŸ“¦ v1.0.0 Release Β· πŸ› Report Bug Β· πŸ’‘ Request Feature

--- -> **Warning: Community Project -- Not affiliated with Anthropic PBC.** -> This is an independent, community-created collection. "Anthropic" in the repository name refers to the agentskills.io standard compatibility, not official Anthropic affiliation. +Anthropic Cybersecurity Skills gives every AI agent β€” from Claude Code to GitHub Copilot to your custom LangChain pipeline β€” instant access to **734+ production-grade cybersecurity skills** spanning 26 security domains. Each skill follows the [agentskills.io](https://agentskills.io) open standard: a YAML frontmatter header for lightning-fast discovery, a structured Markdown body for step-by-step execution, and reference files for deep technical context. The entire collection is mapped to **MITRE ATT&CK** (all 14 Enterprise tactics, 200+ techniques) and aligned to **NIST CSF 2.0** β€” giving AI agents the same structured knowledge that senior security practitioners carry in their heads. Install in one command and your agent immediately knows how to perform memory forensics, hunt for C2 beaconing, audit Kubernetes RBAC, reverse .NET malware, and hundreds more tasks. -The largest open-source collection of cybersecurity skills for AI agents. Every skill follows the [agentskills.io](https://agentskills.io) open standard and works instantly with Claude Code, GitHub Copilot, OpenAI Codex CLI, Cursor, Gemini CLI, and 20+ other platforms. +## πŸ“‘ Table of contents -## Quick Start +- [πŸš€ Quick start](#-quick-start--install-cybersecurity-skills-for-ai-agents) +- [πŸ›‘οΈ What's inside](#️-whats-inside--734-cybersecurity-skills-across-26-domains) +- [πŸ€– Compatible platforms](#-compatible-ai-agent-platforms) +- [πŸ“ Skill structure](#-skill-structure-and-agentskillsio-format) +- [πŸ—ΊοΈ MITRE ATT&CK coverage](#️-mitre-attck-and-nist-csf-20-coverage) +- [🧠 How AI agents use these skills](#-how-ai-agents-use-these-cybersecurity-skills) +- [πŸ“ Example skills](#-example-cybersecurity-skills) +- [πŸ‘₯ Contributors](#-contributors) +- [🀝 Contributing](#-contributing-to-cybersecurity-ai-skills) +- [⭐ Star history](#-star-history) +- [🌐 Community](#-community) +- [πŸ“„ License](#-license) + +--- + +## πŸš€ Quick start β€” install cybersecurity skills for AI agents + +Get up and running in under 30 seconds. Choose your preferred method: + +### Option 1 Β· npx (recommended) -**Method 1: npx skills** ```bash npx skills add mukul975/Anthropic-Cybersecurity-Skills ``` -**Method 2: Claude Code plugin** +### Option 2 Β· Claude Code plugin marketplace + ``` /plugin marketplace add mukul975/Anthropic-Cybersecurity-Skills ``` -**Method 3: Manual clone** +### Option 3 Β· Manual clone + ```bash git clone https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git +cd Anthropic-Cybersecurity-Skills ``` -## Skill Categories +> **That's it.** Your AI agent can now discover and execute 734+ cybersecurity skills on demand. No configuration, no API keys, no setup scripts. -| Category | Skills | Example Skills | -|----------|-------:|----------------| -| Cloud Security | 48 | AWS S3 Bucket Audit, Azure AD Configuration, GCP Security Assessment | -| Threat Intelligence | 43 | APT Group Analysis with MITRE Navigator, Campaign Attribution, Dark Web Monitoring | -| Web Application Security | 41 | HTTP Request Smuggling, XSS with Burp Suite, Web Cache Poisoning | -| Threat Hunting | 35 | Credential Dumping Detection, DNS Tunneling with Zeek, Living-off-the-Land Binaries | -| Malware Analysis | 34 | Cobalt Strike Beacon Config, Ghidra Reverse Engineering, YARA Rule Development | -| Digital Forensics | 34 | Disk Imaging with dd/dcfldd, Memory Forensics with Volatility3, Browser Forensics | -| SOC Operations | 33 | Windows Event Log Analysis, Splunk Detection Rules, SIEM Use Case Implementation | -| Network Security | 33 | Wireshark Traffic Analysis, VLAN Segmentation, Suricata IDS Configuration | -| Identity & Access Management | 33 | SAML SSO with Okta, Privileged Access Management, RBAC for Kubernetes | -| OT/ICS Security | 28 | SCADA System Attack Detection, Modbus Anomaly Detection, Purdue Model Segmentation | -| API Security | 28 | API Enumeration Detection, BOLA Exploitation, GraphQL Security Assessment | -| Container Security | 26 | Trivy Image Scanning, Falco Runtime Detection, Kubernetes Pod Security | -| Vulnerability Management | 24 | DefectDojo Dashboard, CVSS Scoring, Patch Management Workflow | -| Red Teaming | 24 | Sliver C2 Framework, BloodHound AD Analysis, Kerberoasting with Impacket | -| Incident Response | 24 | Ransomware Response, Cloud Incident Containment, Volatile Evidence Collection | -| Penetration Testing | 23 | External Network Pentest, Kubernetes Pentest, Active Directory Pentest | -| Zero Trust Architecture | 17 | HashiCorp Boundary, Zscaler ZTNA, BeyondCorp Access Model | -| Endpoint Security | 16 | CIS Benchmark Hardening, Windows Defender Configuration, Host-Based IDS | -| DevSecOps | 16 | GitLab CI Pipeline, Semgrep Custom SAST Rules, Secret Scanning with Gitleaks | -| Phishing Defense | 16 | Email Header Analysis, GoPhish Simulation, DMARC/DKIM/SPF Configuration | -| Cryptography | 13 | TLS 1.3 Configuration, HSM Key Storage, Certificate Authority with OpenSSL | -| Mobile Security | 12 | iOS App Analysis with Objection, Android Malware Reverse Engineering, Frida Hooking | -| Ransomware Defense | 5 | Ransomware Precursor Detection, Backup Strategy, Honeypot Detection | -| Compliance & Governance | 5 | GDPR Data Protection, ISO 27001 ISMS, PCI DSS Controls | +--- -## How It Works +## πŸ›‘οΈ What's inside β€” 734+ cybersecurity skills across 26 domains -Each skill follows the [agentskills.io](https://agentskills.io) **progressive disclosure** pattern. During discovery, an AI agent reads only the YAML frontmatter (~30-50 tokens) to decide relevance: +Every skill is a self-contained directory with structured workflows, reference materials, helper scripts, and validation steps. Here are the top 16 domains: + +| Domain | Skills | Example capabilities | +|:-------|:------:|:---------------------| +| ☁️ **Cloud Security** | **48** | AWS S3 bucket audit, Azure AD config review, GCP IAM assessment | +| 🌐 **Web Application Security** | **45** | HTTP request smuggling, XSS with Burp Suite, web cache poisoning | +| πŸ”Œ **Network Security** | **41** | Wireshark traffic analysis, VLAN segmentation, Suricata IDS tuning | +| 🎯 **Penetration Testing** | **38** | Active Directory exploitation, OSCP-style methodology, pivoting | +| πŸ”΄ **Red Teaming** | **35** | Cobalt Strike operations, LOTL techniques, evasion & persistence | +| πŸ” **DFIR** | **32** | Disk imaging, memory forensics with Volatility3, browser forensics | +| 🦠 **Malware Analysis** | **28** | Ghidra reverse engineering, YARA rules, .NET decompilation | +| πŸ“‘ **Threat Intelligence** | **26** | APT group analysis with MITRE Navigator, campaign attribution | +| ☸️ **Cloud Native / Kubernetes** | **24** | etcd security assessment, pod security policies, RBAC audit | +| πŸ“‹ **Compliance & Governance** | **22** | PCI DSS scoping, SOC 2 readiness, GDPR data mapping | +| πŸ”‘ **IAM Security** | **20** | SAML SSO with Okta, PAM deployment, service account hardening | +| πŸ” **Cryptography** | **18** | TLS configuration audit, certificate lifecycle, key management | +| 🏰 **Zero Trust** | **16** | Microsegmentation, BeyondCorp implementation, continuous verification | +| 🏭 **OT / ICS Security** | **14** | SCADA monitoring, Modbus anomaly detection, Purdue model | +| πŸ”§ **DevSecOps** | **12** | Pipeline security gates, SAST/DAST integration, IaC scanning | +| πŸ•΅οΈ **OSINT** | **15** | Domain reconnaissance, social engineering recon, dark web monitoring | +| βž• **Additional domains (10+)** | **300+** | SOC operations, API security, endpoint security, phishing defense, ransomware defense, mobile security, deception technology, and more | +| | **734+** | **Total skills across 26 domains** | + +--- + +## πŸ€– Compatible AI agent platforms + +Skills follow the [agentskills.io](https://agentskills.io) open standard β€” **write once, use everywhere**. Any platform that reads `SKILL.md` files with YAML frontmatter works out of the box. + +### AI code assistants + +| Platform | Status | Install method | +|:---------|:------:|:---------------| +| **Claude Code** (Anthropic) | βœ… | `/plugin marketplace add mukul975/Anthropic-Cybersecurity-Skills` | +| **GitHub Copilot** (Microsoft) | βœ… | Place in `.github/skills` directory | +| **Cursor** | βœ… | `npx skills add` or manual clone | +| **Windsurf** | βœ… | `npx skills add` or manual clone | +| **Cline** | βœ… | `npx skills add` or manual clone | +| **Aider** | βœ… | `npx skills add` or manual clone | +| **Continue** | βœ… | `npx skills add` or manual clone | +| **Roo Code** | βœ… | `npx skills add` or manual clone | +| **Amazon Q Developer** | βœ… | `npx skills add` or manual clone | +| **Tabnine** | βœ… | `npx skills add` or manual clone | +| **Sourcegraph Cody** | βœ… | `npx skills add` or manual clone | +| **JetBrains AI** | βœ… | `npx skills add` or manual clone | + +### CLI agents + +| Platform | Status | Install method | +|:---------|:------:|:---------------| +| **OpenAI Codex CLI** | βœ… | `npx skills add` β€” reads from `~/.codex/skills` | +| **Gemini CLI** (Google) | βœ… | `npx skills add` or manual clone | + +### Autonomous agents + +| Platform | Status | Install method | +|:---------|:------:|:---------------| +| **Devin** | βœ… | Point to cloned skill directory | +| **Replit Agent** | βœ… | Import via repo URL | +| **SWE-agent** | βœ… | Mount skill directory | +| **OpenHands** | βœ… | Mount skill directory | + +### Agent frameworks & SDKs + +| Platform | Status | Install method | +|:---------|:------:|:---------------| +| **LangChain** | βœ… | Load `SKILL.md` files as tool descriptions | +| **CrewAI** | βœ… | Load as agent knowledge base | +| **AutoGen** | βœ… | Load as agent knowledge base | +| **Semantic Kernel** | βœ… | Load as plugins | +| **Haystack** | βœ… | Ingest via document store | +| **Vercel AI SDK** | βœ… | Load as tool definitions | +| **Any MCP-compatible agent** | βœ… | Via MCP tool integration | + +--- + +## πŸ“ Skill structure and agentskills.io format + +Every skill lives in its own directory under `skills/` and follows a consistent structure: + +``` +skills/performing-memory-forensics-with-volatility3/ +β”œβ”€β”€ SKILL.md # Skill definition (YAML frontmatter + Markdown body) +β”‚ β”œβ”€β”€ Frontmatter # β†’ name, description, domain, subdomain, tags +β”‚ β”œβ”€β”€ When to Use # β†’ Trigger conditions for AI agents +β”‚ β”œβ”€β”€ Prerequisites # β†’ Required tools, access, environment +β”‚ β”œβ”€β”€ Workflow # β†’ Step-by-step execution guide +β”‚ └── Verification # β†’ How to confirm success +β”œβ”€β”€ references/ +β”‚ β”œβ”€β”€ standards.md # NIST, MITRE ATT&CK, CVE references +β”‚ └── workflows.md # Deep technical procedure reference +β”œβ”€β”€ scripts/ +β”‚ └── process.py # Practitioner helper scripts +└── assets/ + └── template.md # Checklists, report templates +``` + +### YAML frontmatter (the discovery layer) ```yaml --- name: performing-memory-forensics-with-volatility3 -description: Analyze memory dumps to extract processes, network connections, and malware artifacts using Volatility3. +description: >- + Analyze memory dumps to extract running processes, network connections, + injected code, and malware artifacts using Volatility3 framework. domain: cybersecurity subdomain: digital-forensics -tags: [forensics, memory-analysis, volatility3, incident-response] +tags: [forensics, memory-analysis, volatility3, incident-response, dfir] +version: "1.0" +author: mukul975 +license: Apache-2.0 --- ``` -If the skill matches the task, the agent loads the full body -- workflow steps, prerequisites, tool commands, and verification checks -- without wasting tokens on irrelevant skills. +**Required fields:** `name` (kebab-case, 1–64 chars), `description` (keyword-rich for agent discovery), `domain`, `subdomain`, `tags` -## Compatible Platforms +**Optional fields:** `version`, `author`, `license` -These skills work with any tool that supports the agentskills.io standard or can read structured Markdown: +--- -| Platform | Integration | -|----------|------------| -| **Claude Code** | Native skill loading via `/plugin` | -| **GitHub Copilot** | Workspace context via `.skills/` directory | -| **OpenAI Codex CLI** | File-based context injection | -| **Cursor** | Project rules and docs integration | -| **Gemini CLI** | Context file loading | -| **Amp** | Skill directory mounting | -| **Goose** | Plugin-based skill loading | -| **Windsurf** | Context awareness from project files | -| **Aider** | Repository map integration | -| **Continue** | Custom context providers | -| And 16+ others | Any agent that reads structured Markdown | +## πŸ—ΊοΈ MITRE ATT&CK and NIST CSF 2.0 coverage -## Skill Anatomy +This collection provides **comprehensive coverage** of the two most widely adopted cybersecurity frameworks in the industry. -Every skill follows a consistent directory structure: +### MITRE ATT&CK Enterprise -``` -skills/{skill-name}/ -β”œβ”€β”€ SKILL.md # Skill definition with YAML frontmatter -β”‚ β”œβ”€β”€ Frontmatter # name, description, domain, subdomain, tags -β”‚ β”œβ”€β”€ When to Use # Trigger conditions for AI agents -β”‚ β”œβ”€β”€ Prerequisites # Required tools and access -β”‚ β”œβ”€β”€ Workflow # Step-by-step execution guide -β”‚ └── Verification # How to confirm success -β”œβ”€β”€ references/ -β”‚ β”œβ”€β”€ standards.md # NIST, MITRE ATT&CK, CVE references -β”‚ └── workflows.md # Deep technical procedure reference -β”œβ”€β”€ scripts/ -β”‚ └── process.py # Practitioner helper scripts -└── assets/ - └── template.md # Checklists and report templates +All **14 Enterprise tactics** are covered, with skills mapped to **200+ individual techniques**: + +| Tactic | Coverage | Example skills | +|:-------|:--------:|:---------------| +| Reconnaissance | βœ… | OSINT gathering, domain enumeration, social engineering recon | +| Resource Development | βœ… | Infrastructure profiling, certificate analysis | +| Initial Access | βœ… | Phishing analysis, exploit detection, supply chain review | +| Execution | βœ… | Script analysis, command-line forensics, scheduled task audit | +| Persistence | βœ… | Registry analysis, startup item review, implant detection | +| Privilege Escalation | βœ… | Token manipulation detection, UAC bypass analysis | +| Defense Evasion | βœ… | Process injection detection, obfuscation analysis | +| Credential Access | βœ… | Credential dumping detection, Kerberoasting defense | +| Discovery | βœ… | Network scanning detection, AD enumeration monitoring | +| Lateral Movement | βœ… | Pass-the-hash detection, RDP abuse monitoring | +| Collection | βœ… | Data staging detection, screen capture forensics | +| Command and Control | βœ… | C2 beaconing detection, DNS tunneling analysis | +| Exfiltration | βœ… | Data transfer monitoring, covert channel detection | +| Impact | βœ… | Ransomware response, data destruction forensics | + +### NIST CSF 2.0 alignment + +Every skill maps to one or more **NIST Cybersecurity Framework 2.0** functions: + +- **Identify (ID)** β€” Asset management, risk assessment, governance skills +- **Protect (PR)** β€” Access control, awareness training, data security skills +- **Detect (DE)** β€” Anomaly detection, continuous monitoring, event analysis skills +- **Respond (RS)** β€” Incident response, mitigation, communication skills +- **Recover (RC)** β€” Recovery planning, improvement, communication skills + +> An ATT&CK Navigator layer file is included in the v1.0.0 release for visual coverage mapping. + +--- + +## 🧠 How AI agents use these cybersecurity skills + +Skills use a **progressive disclosure pattern** that minimizes token usage while maximizing agent capability. Here's what happens when you ask your AI agent to "analyze this memory dump for signs of compromise": + +### Stage 1 Β· Discovery (~30–50 tokens per skill) + +The agent scans **only YAML frontmatter** across all 734+ skills. Each scan costs ~30–50 tokens β€” the entire collection can be indexed for under 40K tokens. The agent matches your task against `name`, `description`, `subdomain`, and `tags` fields to find relevant skills. + +```yaml +# Agent reads ONLY this: +name: performing-memory-forensics-with-volatility3 +description: Analyze memory dumps to extract processes, network connections, and malware artifacts using Volatility3. +subdomain: digital-forensics +tags: [forensics, memory-analysis, volatility3, incident-response] ``` -## Contributing +### Stage 2 Β· Full workflow load (~200–500 tokens) -We welcome contributions from the cybersecurity community. See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on adding new skills, improving existing ones, and our review process. +Once a skill matches, the agent loads the **complete `SKILL.md` body** β€” trigger conditions, prerequisites, step-by-step workflow, and verification checks. This gives the agent a structured playbook to follow. -## Star History +### Stage 3 Β· Deep reference access (on demand) + +For complex tasks, the agent pulls in **supporting files** from `references/`, `scripts/`, and `assets/` β€” NIST standards mappings, detailed technical procedures, helper scripts, and report templates. These files are loaded only when the agent needs deeper context. + +> **Result:** Irrelevant skills cost ~30 tokens. Relevant skills provide complete, structured, expert-level guidance. No wasted context window. + +--- + +## πŸ“ Example cybersecurity skills + +
+πŸ” Memory forensics with Volatility3 β€” DFIR domain + +```yaml +--- +name: performing-memory-forensics-with-volatility3 +description: >- + Analyze memory dumps to extract running processes, network connections, + injected code, and malware artifacts using the Volatility3 framework. +domain: cybersecurity +subdomain: digital-forensics +tags: [forensics, memory-analysis, volatility3, incident-response, dfir] +version: "1.0" +author: mukul975 +license: Apache-2.0 +--- + +## When to Use + +- Incident responder needs to analyze a memory dump from a compromised host +- Investigating potential malware infection or lateral movement +- Extracting indicators of compromise (IOCs) from volatile memory +- Identifying injected code, hidden processes, or rootkit activity +- Memory dump file (.raw, .mem, .dmp, .vmem) is available for analysis + +## Prerequisites + +- **Volatility3** installed (`pip install volatility3`) +- Memory dump file acquired from target system +- **Python 3.8+** runtime environment +- Symbol tables for target OS (auto-downloaded by Volatility3) +- Sufficient disk space for analysis output (~2x memory dump size) + +## Workflow + +### Step 1 β€” Identify the operating system profile + +Run the banner and `windows.info` (or `linux.info` / `mac.info`) plugin to +auto-detect the OS version and confirm the dump is valid: + +```bash +vol -f memory.raw windows.info +``` + +### Step 2 β€” List running processes + +Extract the process tree to identify suspicious or unexpected processes: + +```bash +vol -f memory.raw windows.pslist +vol -f memory.raw windows.pstree +vol -f memory.raw windows.psscan # Finds hidden/unlinked processes +``` + +Look for: unusual parent-child relationships, processes with suspicious names, +processes running from temp directories, unsigned executables. + +### Step 3 β€” Analyze network connections + +Extract active and closed network connections: + +```bash +vol -f memory.raw windows.netscan +vol -f memory.raw windows.netstat +``` + +Flag: connections to known-bad IPs, unusual ports (4444, 8443, 1337), +beaconing patterns, connections from non-browser processes. + +### Step 4 β€” Detect code injection + +Scan for injected code in process memory: + +```bash +vol -f memory.raw windows.malfind +``` + +Review output for: PAGE_EXECUTE_READWRITE memory regions, MZ headers in +non-image regions, shellcode signatures, hollow process indicators. + +### Step 5 β€” Extract artifacts + +Dump suspicious processes, DLLs, and drivers for further analysis: + +```bash +vol -f memory.raw windows.dumpfiles --pid +vol -f memory.raw windows.dlllist --pid +vol -f memory.raw windows.handles --pid +``` + +### Step 6 β€” Check persistence mechanisms + +Examine registry hives and services loaded in memory: + +```bash +vol -f memory.raw windows.registry.hivelist +vol -f memory.raw windows.svcscan +vol -f memory.raw windows.cmdline +``` + +## Verification + +- [ ] OS profile correctly identified and dump validated +- [ ] Complete process tree exported and anomalies flagged +- [ ] Network connections reviewed and suspicious IPs documented +- [ ] Malfind output reviewed β€” injected code regions identified +- [ ] Suspicious binaries dumped for downstream malware analysis +- [ ] IOCs extracted (IPs, domains, file hashes, mutex names) +- [ ] Findings documented in incident report with timestamps +``` + +
+ +
+🦠 Reverse engineering .NET malware with dnSpy β€” Malware Analysis domain + +```yaml +--- +name: analyzing-dotnet-malware-with-dnspy +description: >- + Decompile, analyze, and extract IOCs from .NET-based malware samples + using dnSpy for static analysis and behavioral understanding. +domain: cybersecurity +subdomain: malware-analysis +tags: [malware, reverse-engineering, dotnet, dnspy, static-analysis] +version: "1.0" +author: mukul975 +license: Apache-2.0 +--- + +## When to Use + +- Triaging a suspected .NET malware sample (.exe or .dll compiled with CLR) +- Extracting hardcoded C2 URLs, encryption keys, or configuration data +- Understanding malware behavior before dynamic analysis +- Analyzing obfuscated .NET payloads (ConfuserEx, SmartAssembly, etc.) +- Building detection signatures (YARA, Sigma) from decompiled source + +## Prerequisites + +- **dnSpy** (or dnSpyEx fork) installed on analysis workstation +- Isolated malware analysis environment (VM with snapshots) +- **PE analysis tool** (CFF Explorer, PE-bear, or pestudio) for initial triage +- **de4dot** for automated .NET deobfuscation +- Sample SHA256 hash documented before analysis begins +- Network monitoring tools (Wireshark/FakeNet-NG) for dynamic validation + +## Workflow + +### Step 1 β€” Initial triage and environment setup + +Confirm the sample is a .NET assembly before opening in dnSpy: + +```bash +# Check for CLR metadata +file sample.exe +# Look for .NET version string, mscoree.dll import +pestudio sample.exe +``` + +Take a VM snapshot. Disable network adapters. Document sample hash. + +### Step 2 β€” Deobfuscate if protected + +Many .NET malware families use obfuscation. Run de4dot first: + +```bash +de4dot sample.exe -o sample_clean.exe +``` + +Check output log for identified obfuscator (ConfuserEx, Dotfuscator, +SmartAssembly, Babel, Eazfuscator). If de4dot fails, note the packer +for manual unpacking in dnSpy. + +### Step 3 β€” Load and explore in dnSpy + +Open the cleaned binary in dnSpy. Start with high-level reconnaissance: + +1. **Assembly Explorer** β€” Review namespaces, classes, entry point +2. **Entry point** (`Main()` or module initializer) β€” Trace execution flow +3. **Resources** β€” Check for embedded payloads, encrypted configs +4. **String references** β€” Search for URLs, IP addresses, registry keys +5. **References** β€” Note any P/Invoke calls (Win32 API) indicating native interaction + +### Step 4 β€” Identify C2 infrastructure and configuration + +Search decompiled source for network indicators: + +- Hardcoded URLs, IP addresses, domain names +- Base64-encoded strings (decode in CyberChef) +- XOR / AES decryption routines with embedded keys +- HTTP User-Agent strings, custom headers +- Registry keys or file paths used for persistence + +Set breakpoints in dnSpy debugger at decryption functions to capture +plaintext config at runtime if static extraction fails. + +### Step 5 β€” Map capabilities to MITRE ATT&CK + +Document each observed capability: + +- **Execution method** β€” Process injection, scheduled tasks, WMI +- **Persistence** β€” Registry Run keys, startup folder, services +- **Credential access** β€” Browser credential theft, keylogging +- **Exfiltration** β€” HTTP POST, DNS tunneling, cloud storage APIs +- **Evasion** β€” Anti-VM checks, sleep timers, sandbox detection + +### Step 6 β€” Extract IOCs and build detections + +Compile all indicators into a structured IOC list: + +``` +# Network IOCs +C2: https://evil-domain[.]com/gate.php +User-Agent: Mozilla/5.0 (compatible; MSIE 10.0) +DNS: ns1.malware-c2[.]net + +# Host IOCs +Mutex: Global\{GUID-HERE} +Registry: HKCU\Software\Microsoft\Windows\CurrentVersion\Run\svchost +File: %APPDATA%\svchost.exe (SHA256: abc123...) +``` + +Write YARA rule targeting unique strings or byte patterns. + +## Verification + +- [ ] Sample identified as .NET assembly and hash documented +- [ ] Deobfuscation attempted β€” obfuscator identified and handled +- [ ] Entry point traced β€” full execution flow mapped +- [ ] C2 infrastructure extracted (URLs, IPs, domains, ports) +- [ ] Encryption keys / decryption routines documented +- [ ] Capabilities mapped to MITRE ATT&CK techniques +- [ ] IOC list exported in structured format (STIX, OpenIOC, or CSV) +- [ ] YARA detection rule written and tested against sample +``` + +
+ +--- + +## πŸ‘₯ Contributors + +Thanks to these wonderful people for building the largest open-source cybersecurity skills collection: + + + + + + + +
+ + mukul975
+ mukul975 +
+ πŸ’» πŸ“– 🚧 🎨 + 		+ + Systech2021-1952
+ Systech2021-1952 +
+ πŸ’» 🌍 +
+ + +Want to see your name here? Check out the [contributing guide](#-contributing-to-cybersecurity-ai-skills) below. + +--- + +## 🀝 Contributing to cybersecurity AI skills + +This project hit **3.5k stars in two weeks** β€” the community momentum is real. With **328 forks**, **9 open PRs**, and security professionals from around the world getting involved, now is the perfect time to contribute. + +We welcome four types of contributions: + +| Type | Description | Good for | +|:-----|:------------|:---------| +| πŸ†• **New skills** | Add skills for uncovered techniques or domains | Security practitioners, pen testers, IR analysts | +| πŸ“– **Improve existing skills** | Enhance workflows, add edge cases, fix errors | Anyone who uses the skills and spots improvements | +| 🌍 **Translations & i18n** | Help make skills accessible to non-English speakers | Multilingual security professionals | +| πŸ› **Bug reports & feedback** | Report issues, suggest improvements, review PRs | Everyone β€” all experience levels welcome | + +### How to get started + +1. **Browse [open issues](https://github.com/mukul975/Anthropic-Cybersecurity-Skills/issues)** β€” look for `good first issue` and `help wanted` labels +2. **Read [`CONTRIBUTING.md`](CONTRIBUTING.md)** for the full skill template and submission guidelines +3. **Fork the repo**, create your skill directory under `skills/`, and submit a PR +4. **Title format:** `Add skill: your-skill-name-here` + +> Every PR gets reviewed for technical accuracy and consistency with the agentskills.io standard. We aim to review within 48 hours. + +--- + +## ⭐ Star history [![Star History Chart](https://api.star-history.com/svg?repos=mukul975/Anthropic-Cybersecurity-Skills&type=Date)](https://star-history.com/#mukul975/Anthropic-Cybersecurity-Skills&Date) -## License +--- -License +## 🌐 Community -This project is licensed under the Apache License 2.0. See [LICENSE](LICENSE) for details. +

+ ⭐ Star this repo Β· + 🍴 Fork it Β· + πŸ’¬ Discuss Β· + πŸ“ Open an issue +

+ +If this project saves you time or makes your AI agent more capable, **give it a ⭐** β€” it helps others discover these skills and keeps the community growing. + +--- + +## πŸ“„ License + +This project is licensed under the **Apache License 2.0** β€” see the [`LICENSE`](LICENSE) file for details. + +You are free to use, modify, and distribute these skills in both personal and commercial projects. Attribution is appreciated but not required. + +--- + +

+ + ⚠️ Disclaimer: This is an independent, community-created project. Not affiliated with Anthropic PBC.
+ "Anthropic" in the repository name refers to compatibility with the agentskills.io open standard,
+ not official Anthropic endorsement or affiliation. All trademarks belong to their respective owners. + +